Shitao commited on
Commit
c2997b7
1 Parent(s): ba6e4ad

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -30,8 +30,8 @@ And the score can be mapped to a float value in [0,1] by sigmoid function.
30
  | [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) | [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) | Chinese and English | - | Lightweight reranker model, easy to deploy, with fast inference. |
31
  | [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) | [xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) | Chinese and English | - | Lightweight reranker model, easy to deploy, with fast inference. |
32
  | [BAAI/bge-reranker-v2-m3](https://huggingface.co/BAAI/bge-reranker-v2-m3) | [bge-m3](https://huggingface.co/BAAI/bge-m3) | Multilingual | - | Lightweight reranker model, possesses strong multilingual capabilities, easy to deploy, with fast inference. |
33
- | [BAAI/bge-reranker-v2-gemma](https://huggingface.co/BAAI/bge-reranker-v2-gemma) | [google/gemma-2b](https://huggingface.co/google/gemma-2b) | Multilingual | - | Suitable for multilingual contexts, performs well in both English proficiency and multilingual capabilities. |
34
- | [BAAI/bge-reranker-v2-minicpm-layerwise](https://huggingface.co/BAAI/bge-reranker-v2-minicpm-layerwise) | [openbmb/MiniCPM-2B-dpo-fp16](https://huggingface.co/openbmb/MiniCPM-2B-dpo-fp16/tree/main) | Multilingual | 8-40 | Suitable for multilingual contexts, performs well in both English and Chinese proficiency, allows freedom to select layers for output, facilitating accelerated inference. |
35
 
36
 
37
  You can select the model according your senario and resource.
@@ -267,7 +267,7 @@ You can fine-tune the reranker with the following code:
267
  torchrun --nproc_per_node {number of gpus} \
268
  -m FlagEmbedding.llm_reranker.finetune_for_instruction.run \
269
  --output_dir {path to save model} \
270
- --model_name_or_path BAAI/bge-reranker-v2-gemma \
271
  --train_data ./toy_finetune_data.jsonl \
272
  --learning_rate 2e-4 \
273
  --num_train_epochs 1 \
@@ -298,7 +298,7 @@ torchrun --nproc_per_node {number of gpus} \
298
  torchrun --nproc_per_node {number of gpus} \
299
  -m FlagEmbedding.llm_reranker.finetune_for_layerwise.run \
300
  --output_dir {path to save model} \
301
- --model_name_or_path BAAI/bge-reranker-v2-minicpm-layerwise \
302
  --train_data ./toy_finetune_data.jsonl \
303
  --learning_rate 2e-4 \
304
  --num_train_epochs 1 \
@@ -326,7 +326,7 @@ torchrun --nproc_per_node {number of gpus} \
326
  --head_type simple
327
  ```
328
 
329
- Our rerankers are initialized from [google/gemma-2b](https://huggingface.co/google/gemma-2b) (for llm-based reranker) and [openbmb/MiniCPM-2B-dpo-fp16](https://huggingface.co/openbmb/MiniCPM-2B-dpo-fp16/tree/main) (for llm-based layerwise reranker), and we train it on a mixture of multilingual datasets:
330
 
331
  - [bge-m3-data](https://huggingface.co/datasets/Shitao/bge-m3-data)
332
  - [quora train data](https://huggingface.co/datasets/quora)
 
30
  | [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) | [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) | Chinese and English | - | Lightweight reranker model, easy to deploy, with fast inference. |
31
  | [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) | [xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) | Chinese and English | - | Lightweight reranker model, easy to deploy, with fast inference. |
32
  | [BAAI/bge-reranker-v2-m3](https://huggingface.co/BAAI/bge-reranker-v2-m3) | [bge-m3](https://huggingface.co/BAAI/bge-m3) | Multilingual | - | Lightweight reranker model, possesses strong multilingual capabilities, easy to deploy, with fast inference. |
33
+ | [BAAI/bge-reranker-v2-gemma](https://huggingface.co/BAAI/bge-reranker-v2-gemma) | [gemma-2b](https://huggingface.co/google/gemma-2b) | Multilingual | - | Suitable for multilingual contexts, performs well in both English proficiency and multilingual capabilities. |
34
+ | [BAAI/bge-reranker-v2-minicpm-layerwise](https://huggingface.co/BAAI/bge-reranker-v2-minicpm-layerwise) | [MiniCPM-2B-dpo-bf16](https://huggingface.co/openbmb/MiniCPM-2B-dpo-bf16) | Multilingual | 8-40 | Suitable for multilingual contexts, performs well in both English and Chinese proficiency, allows freedom to select layers for output, facilitating accelerated inference. |
35
 
36
 
37
  You can select the model according your senario and resource.
 
267
  torchrun --nproc_per_node {number of gpus} \
268
  -m FlagEmbedding.llm_reranker.finetune_for_instruction.run \
269
  --output_dir {path to save model} \
270
+ --model_name_or_path google/gemma-2b \
271
  --train_data ./toy_finetune_data.jsonl \
272
  --learning_rate 2e-4 \
273
  --num_train_epochs 1 \
 
298
  torchrun --nproc_per_node {number of gpus} \
299
  -m FlagEmbedding.llm_reranker.finetune_for_layerwise.run \
300
  --output_dir {path to save model} \
301
+ --model_name_or_path openbmb/MiniCPM-2B-dpo-bf16 \
302
  --train_data ./toy_finetune_data.jsonl \
303
  --learning_rate 2e-4 \
304
  --num_train_epochs 1 \
 
326
  --head_type simple
327
  ```
328
 
329
+ Our rerankers are initialized from [google/gemma-2b](https://huggingface.co/google/gemma-2b) (for llm-based reranker) and [openbmb/MiniCPM-2B-dpo-bf16](https://huggingface.co/openbmb/MiniCPM-2B-dpo-bf16) (for llm-based layerwise reranker), and we train it on a mixture of multilingual datasets:
330
 
331
  - [bge-m3-data](https://huggingface.co/datasets/Shitao/bge-m3-data)
332
  - [quora train data](https://huggingface.co/datasets/quora)